Hypergraph-partitioning-based decomposition for parallel sparse-matrix vector multiplication

Simple item page
buir.contributor.authorAykanat, Cevdet
dc.citation.epage693en_US
dc.citation.issueNumber7en_US
dc.citation.spage673en_US
dc.citation.volumeNumber10en_US
dc.contributor.authorCatalyurek, U.V.en_US
dc.contributor.authorAykanat, Cevdeten_US
dc.date.accessioned2016-02-08T10:40:07Z
dc.date.available2016-02-08T10:40:07Zen_US
dc.date.issued1999en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractIn this work, we show that the standard graph-partitioning-based decomposition of sparse matrices does not reflect the actual communication volume requirement for parallel matrix-vector multiplication. We propose two computational hypergraph models which avoid this crucial deficiency of the graph model. The proposed models reduce the decomposition problem to the well-known hypergraph partitioning problem. The recently proposed successful multilevel framework is exploited to develop a multilevel hypergraph partitioning tool PaToH for the experimental verification of our proposed hypergraph models. Experimental results on a wide range of realistic sparse test matrices confirm the validity of the proposed hypergraph models. In the decomposition of the test matrices, the hypergraph models using PaToH and hMeTiS result in up to 63 percent less communication volume (30 to 38 percent less on the average) than the graph model using MeTiS, while PaToH is only 1.3-2.3 times slower than MeTiS on the average.en_US
dc.identifier.doi10.1109/71.780863en_US
dc.identifier.eissn1558-2183
dc.identifier.issn1045-9219
dc.identifier.urihttp://hdl.handle.net/11693/25158en_US
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/71.780863en_US
dc.source.titleIEEE Transactions on Parallel and Distributed Systemsen_US
dc.subjectComputational hypergraph modelsen_US
dc.subjectHypergraph partitioningen_US
dc.subjectHypergraph partitioning based decompositionen_US
dc.subjectParallel sparce matrix vector multiplicationen_US
dc.subjectSparse matricesen_US
dc.subjectComputational methodsen_US
dc.subjectComputer simulationen_US
dc.subjectGraph theoryen_US
dc.subjectMatrix algebraen_US
dc.subjectVectorsen_US
dc.subjectParallel processing systemsen_US
dc.titleHypergraph-partitioning-based decomposition for parallel sparse-matrix vector multiplicationen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Hypergraph-partitioning-based decomposition for parallel sparse-matrix vector multiplication.pdf
Size:
903.95 KB
Format:
Adobe Portable Document Format
Description:
Full Printable Version
Download

Collections

Department of Computer Engineering